Manus AI
Chinese-origin general-purpose autonomous agent launched March 2025 by Butterfly Effect. Operates in a cloud sandbox — browser, file system, shell. Went viral on launch with invite-only access; positioned as a Devin/AutoGPT competitor for non-coding tasks (research, ops, data analysis).
At a glance
- Type
- General-purpose autonomous web/computer agent
- Tier
- T2
- Section
- Agent IDEs & coding harnesses
- Created
- 2025-03
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- $39/$199/mo tier reportedly post-beta
- Funding
- $75M Series A reported (Benchmark + others) at ~$500M val · 2025-mid
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- session
- update
- agent-controlled
- unit
- turn
- governance
- opaque
- conflict
- llm-arbitrate
When to use
Optimised for: autonomous web + file + shell tasks in a cloud sandbox
Anti-fit: not coding-specific; China-origin raises enterprise data-residency concerns for Western buyers
Pros & cons
Pros
Best-known general-purpose autonomous agent of 2025; cloud-sandbox model gives users a hands-off experience.
Cons
Invite-only access; China/Singapore HQ creates buyer hesitation for regulated Western enterprises; no public API at launch.
Claims & capabilities
Butterfly Effect; viral launch Mar 2025; reportedly raised $75M at $500M val in mid-2025 from Benchmark; invite-only access through 2025.
Technical surface
- API surface
- Web app; API in preview
- Backend storage
- cloud sandbox state per session
- Deployment
- Cloud (browser app)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- per-user cloud sandbox
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other agent ides & coding harnesses in the catalog, ranked by inbound references.
- Bedrock AgentCore (AWS) T2
AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).
- Claude Code (Anthropic) T1
Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.
- GitHub Copilot (Agent Mode) T1
The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.
- Aider (harness) T2
OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.
- Amazon Q Developer T1
Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.
- Anthropic Computer Use T1
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude (reported) + OpenAI
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: Anthropic Claude (reported) + OpenAI